docs: add prometheus + grafana deployment guide

config/observability/prometheus/rbac.yaml

@@ -0,0 +1,31 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: inference-gateway-metrics-reader
+rules:
+- nonResourceURLs:
+  - /metrics
+  - /debug/pprof/*
+  verbs:
+  - get
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: inference-gateway-sa-metrics-reader
+  namespace: monitoring
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: inference-gateway-sa-metrics-reader-role-binding
+  namespace: monitoring
+subjects:
+- kind: ServiceAccount
+  name: inference-gateway-sa-metrics-reader
+  namespace: monitoring
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: inference-gateway-metrics-reader
+---

config/observability/prometheus/values.yaml

@@ -0,0 +1,27 @@
+serviceAccounts:
+  server:
+    create: false
+    name: inference-gateway-sa-metrics-reader
+
+extraScrapeConfigs: |
+  - job_name: 'inference-extension-epp'
+    authorization:
+        credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+    scrape_interval: 5s   
+    kubernetes_sd_configs:
+      - role: endpoints
+    relabel_configs:
+      - source_labels: [__meta_kubernetes_service_name]
+        action: keep
+        regex: .*-epp$
+      - source_labels: [__meta_kubernetes_pod_container_port_number]
+        action: keep
+        regex: "9090"
+  - job_name: vllm
+    scrape_interval: 5s   
+    kubernetes_sd_configs:
+      - role: pod
+    relabel_configs:
+      - source_labels: [__meta_kubernetes_pod_label_app]
+        action: keep
+        regex: vllm-llama3-8b-instruct

site-src/guides/metrics-and-observability.md

@@ -126,6 +126,66 @@ PROFILE_NAME=heap
 curl -H "Authorization: Bearer $TOKEN" localhost:9090/debug/pprof/$PROFILE_NAME -o profile.out
 go tool pprof -png profile.out
 ```
+## Setting Up Grafana + Prometheus
+
+### Grafana
+
+A simple grafana deployment can be done with the following commands:
+
+```bash
+helm repo add grafana https://grafana.github.io/helm-charts
+helm install grafana grafana/grafana --namespace monitoring --create-namespace
+```
+
+Get the Grafana URL to visit by running these commands in the same shell:
+
+```bash
+ export POD_NAME=$(kubectl get pods --namespace monitoring -l "app.kubernetes.io/name=grafana,app.kubernetes.io/instance=grafana" -o jsonpath="{.items[0].metadata.name}")
+ kubectl --namespace monitoring port-forward $POD_NAME 3000
+```
+
+### Prometheus
+
+We currently have 2 types of prometheus deployments documented:
+
+1. Self Hosted using the prometheus helm chart
+2. Using Google Managed Prometheus
+
+=== "Self-Hosted"
+
+    Create Necessary ServiceAccount and RBAC Resources:
+
+     ```bash
+        kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/observability/prometheus/rbac.yaml
+     ```
+
+    Add the prometheus-community helm repository:
+
+     ```bash
+        helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
+     ```
+
+    Deploy the prometheus helm chart using this command:
+     ```bash
+        helm install prometheus prometheus-community/prometheus \
+         --namespace monitoring \
+         -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/observability/prometheus/values.yaml
+     ```
+
+    You can add the prometheus data source to grafana following [This Guide](https://grafana.com/docs/grafana/latest/administration/data-source-management/).
+    The prometheus server host is by default `http://prometheus-server`
+
+    Notice that the given values file is very simple and will work directly after following the [Getting Started Guide](https://gateway-api-inference-extension.sigs.k8s.io/guides/), you might need to modify it
+
+=== "Google Managed"
+
+    If you run the inference gateway with [Google Managed Prometheus](https://cloud.google.com/stackdriver/docs/managed-prometheus), please follow the [instructions](https://cloud.google.com/stackdriver/docs/managed-prometheus/query)
+    to configure Google Managed Prometheus as data source for the grafana dashboard.
+
+## Load Inference Extension dashboard into Grafana
+
+Please follow [grafana instructions](https://grafana.com/docs/grafana/latest/dashboards/build-dashboards/import-dashboards/) to load the dashboard json.
+The dashboard can be found here [Grafana Dashboard](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/tools/dashboards/inference_gateway.json)
 
 ## Prometheus Alerts